Py之pycocotools库的简介、安装、使用方法及说明

pip install pycocotools==2.0.0 or pip install pycocotools-windows

__author__ = 'tylin' __version__ = '2.0' # Interface for accessing the Microsoft COCO dataset. # Microsoft COCO is a large image dataset designed for object detection, # segmentation, and caption generation. pycocotools is a Python API that # assists in loading, parsing and visualizing the annotations in COCO. # Please visit http://mscoco.org/ for more information on COCO, including # for the data, paper, and tutorials. The exact format of the annotations # is also described on the COCO website. For example usage of the pycocotools # please see pycocotools_demo.ipynb. In addition to this API, please download both # the COCO images and annotations in order to run the demo. # An alternative to using the API is to load the annotations directly # into Python dictionary # Using the API provides additional utility functions. Note that this API # supports both *instance* and *caption* annotations. In the case of # captions not all functions are defined (e.g. categories are undefined). # The following API functions are defined: #  COCO       - COCO api class that loads COCO annotation file and prepare data structures. #  decodeMask - Decode binary mask M encoded via run-length encoding. #  encodeMask - Encode binary mask M using run-length encoding. #  getAnnIds  - Get ann ids that satisfy given filter conditions. #  getCatIds  - Get cat ids that satisfy given filter conditions. #  getImgIds  - Get img ids that satisfy given filter conditions. #  loadAnns   - Load anns with the specified ids. #  loadCats   - Load cats with the specified ids. #  loadImgs   - Load imgs with the specified ids. #  annToMask  - Convert segmentation in an annotation to binary mask. #  showAnns   - Display the specified annotations. #  loadRes    - Load algorithm results and create API for accessing them. #  download   - Download COCO images from mscoco.org server. # Throughout the API "ann"=annotation, "cat"=category, and "img"=image. # Help on each functions can be accessed by: "help COCO>function". # See also COCO>decodeMask, # COCO>encodeMask, COCO>getAnnIds, COCO>getCatIds, # COCO>getImgIds, COCO>loadAnns, COCO>loadCats, # COCO>loadImgs, COCO>annToMask, COCO>showAnns # Microsoft COCO Toolbox.      version 2.0 # Data, paper, and tutorials available at:  http://mscoco.org/ # Code written by Piotr Dollar and Tsung-Yi Lin, 2014. # Licensed under the Simplified BSD License [see bsd.txt]

from pycocotools.coco import COCO import matplotlib.pyplot as plt import cv2 import os import numpy as np import random #1、定义数据集路径 cocoRoot = "F:/File_Python/Resources/image/COCO" dataType = "val2017" annFile = os.path.join(cocoRoot, f'annotations/instances_{dataType}.json') print(f'Annotation file: {annFile}') #2、为实例注释初始化COCO的API coco=COCO(annFile) #3、采用不同函数获取对应数据或类别 ids = coco.getCatIds('person')[0]    #采用getCatIds函数获取"person"类别对应的ID print(f'"person" 对应的序号: {ids}') id = coco.getCatIds(['dog'])[0]      #获取某一类的所有图片，比如获取包含dog的所有图片 imgIds = coco.catToImgs[id] print(f'包含dog的图片共有：{len(imgIds)}张, 分别是：',imgIds) cats = coco.loadCats(1)               #采用loadCats函数获取序号对应的类别名称 print(f'"1" 对应的类别名称: {cats}') imgIds = coco.getImgIds(catIds=[1])    #采用getImgIds函数获取满足特定条件的图片（交集），获取包含person的所有图片 print(f'包含person的图片共有：{len(imgIds)}张') #4、将图片进行可视化 imgId = imgIds[10] imgInfo = coco.loadImgs(imgId)[0] print(f'图像{imgId}的信息如下：\n{imgInfo}') imPath = os.path.join(cocoRoot, 'images', dataType, imgInfo['file_name']) im = cv2.imread(imPath) plt.axis('off') plt.imshow(im) plt.show() plt.imshow(im); plt.axis('off') annIds = coco.getAnnIds(imgIds=imgInfo['id'])      # 获取该图像对应的anns的Id print(f'图像{imgInfo["id"]}包含{len(anns)}个ann对象，分别是:\n{annIds}') anns = coco.loadAnns(annIds) coco.showAnns(anns) print(f'ann{annIds[3]}对应的mask如下：') mask = coco.annToMask(anns[3]) plt.imshow(mask); plt.axis('off')